lkml.org 
[lkml]   [2011]   [Jun]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v2] trace: Set __GFP_NORETRY flag for ring buffer allocating process
Date
The tracing ring buffer is allocated from kernel memory. While
allocating a large chunk of memory, OOM might happen which destabilizes
the system. Thus random processes might get killed during the
allocation.

This patch adds __GFP_NORETRY flag to the ring buffer allocation calls
to make it fail more gracefully if the system will not be able to
complete the allocation request.

Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
---
Changelog:
v2-v1: Added comment to explaing use of __GFP_NORETRY

kernel/trace/ring_buffer.c | 25 ++++++++++++++++++++-----
1 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2780e60..bd588b6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1004,8 +1004,14 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,

for (i = 0; i < nr_pages; i++) {
struct page *page;
+ /*
+ * __GFP_NORETRY flag makes sure that the allocation fails
+ * gracefully without invoking oom-killer and the system is
+ * not destabilized.
+ */
bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
- GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
+ GFP_KERNEL | __GFP_NORETRY,
+ cpu_to_node(cpu_buffer->cpu));
if (!bpage)
goto free_pages;

@@ -1014,7 +1020,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
list_add(&bpage->list, &pages);

page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
- GFP_KERNEL, 0);
+ GFP_KERNEL | __GFP_NORETRY, 0);
if (!page)
goto free_pages;
bpage->page = page_address(page);
@@ -1376,13 +1382,20 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
for_each_buffer_cpu(buffer, cpu) {
for (i = 0; i < new_pages; i++) {
struct page *page;
+ /*
+ * __GFP_NORETRY flag makes sure that the allocation
+ * fails gracefully without invoking oom-killer and
+ * the system is not destabilized.
+ */
bpage = kzalloc_node(ALIGN(sizeof(*bpage),
cache_line_size()),
- GFP_KERNEL, cpu_to_node(cpu));
+ GFP_KERNEL | __GFP_NORETRY,
+ cpu_to_node(cpu));
if (!bpage)
goto free_pages;
list_add(&bpage->list, &pages);
- page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL,
+ page = alloc_pages_node(cpu_to_node(cpu),
+ GFP_KERNEL | __GFP_NORETRY,
0);
if (!page)
goto free_pages;
@@ -3737,7 +3750,9 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
struct buffer_data_page *bpage;
struct page *page;

- page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+ page = alloc_pages_node(cpu_to_node(cpu),
+ GFP_KERNEL | __GFP_NORETRY,
+ 0);
if (!page)
return NULL;

--
1.7.3.1


\
 
 \ /
  Last update: 2011-06-08 02:05    [W:0.127 / U:0.116 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site